readygpu

ASUS Ascent GX10 128GB vs NVIDIA GeForce RTX 5090

For running models locally, priced in Canada. At 128k context the first runs 69 models fully in memory, the second 41.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 32 GB. At 128k context the ASUS Ascent GX10 128GB runs 69 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 41; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 6.6× as fast as the ASUS Ascent GX10 128GB (estimated, median across models). In Canada the ASUS Ascent GX10 128GB costs $8,299 at Amazon and the NVIDIA GeForce RTX 5090 $10,300 at Amazon: the ASUS Ascent GX10 128GB is $2,001 cheaper.

Updated . Speeds are estimates; how they are worked out.

ASUS Ascent GX10 128GB

$8,299

Amazon

Add to build
NVIDIA GeForce RTX 5090

$10,300

Amazon

Add to build

Specifications

SpecASUS Ascent GX10 128GBNVIDIA GeForce RTX 5090
ChipGB10 Grace Blackwell–
Memory bus256-bit512-bit
Memory bandwidth273 GB/s1,792 GB/s
FP16 compute62 TFLOPS209 TFLOPS
SoftwareCUDACUDA
Unified memory128 GB–
GPU can use by default119 GB–
GPU can use, tuned122 GB–
Operating systemdgx-os–
Processor20-core Arm (GB10)–
Storage1000 GB–
GPU–GeForce RTX 5090
Memory–32 GB GDDR7
Board power–575 W
PCIe generation–Gen 5
PCIe lanes–x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelASUS Ascent GX10 128GBNVIDIA GeForce RTX 5090
DeepSeek V4 Flash6tok/sUD-Q2_K_XLwon't run
GLM 5.3 Flash10tok/sUD-Q2_K_XLwon't run
Qwen 3.8 Flash Next2tok/sQ4_K_Mwon't run
Qwen 3.8 27B5tok/sQ8_036tok/sUD-Q6_K
MiniMax M2.73tok/sUD-Q2_K_XLwon't run
Qwen 3.5 122B-A10B9tok/sQ6_Koffload
Qwen 3.6 27B5tok/sQ8_036tok/sQ6_K
Qwen3 Coder Next14tok/sQ8_0offload
gpt-oss 120B13tok/sMXFP4won't run
Nemotron 3 Super 120B-A12B8tok/sUD-Q6_Koffload
Gemma 4 31B4tok/sQ8_037tok/sQ4_K_M
Mistral Small 4 119B11tok/sUD-Q6_Koffload
Qwen 3.6 35B-A3B17tok/sQ8_0128tok/sUD-Q6_K
Qwen 3.5 27B5tok/sQ8_036tok/sQ6_K
Gemma 4 26B-A4B14tok/sQ8_095tok/sQ8_0
GLM 4.5 Air3tok/sQ6_Kwon't run
Qwen 3.5 35B-A3B17tok/sQ8_0129tok/sQ6_K
Qwen3 Next 80B-A3B16tok/sQ8_0offload
GLM 4.7 Flash8tok/sQ8_060tok/sQ6_K
Devstral Small 2 24B4tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B24tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B24tok/sQ8_0227tok/sQ4_K_M
gpt-oss 20B18tok/sMXFP4118tok/sMXFP4
Qwen3 Coder 30B-A3B6tok/sQ8_045tok/sQ4_K_M
Qwen3 32B2tok/sQ8_0offload
Gemma 4 12B11tok/sQ8_073tok/sQ8_0
Qwen 3.5 9B12tok/sQ8_080tok/sQ8_0
Gemma 3 27B4tok/sQ8_037tok/sQ5_K_M
Mistral Small 3.2 24B4tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B2tok/sQ8_0offload
Llama 3.3 70B1tok/sQ8_0won't run
Ministral 3 14B5tok/sQ8_036tok/sQ5_K_M
Qwen3 14B5tok/sQ8_035tok/sQ5_K_M
DeepSeek R1 0528 Qwen3 8B6tok/sQ8_040tok/sQ8_0
Qwen3 8B6tok/sQ8_040tok/sQ8_0
Phi-4 14B4tok/sQ8_0offload
Qwen 3.5 4B19tok/sQ8_0126tok/sQ8_0
Ministral 3 8B6tok/sQ8_041tok/sQ8_0
Granite 4.2 8B6tok/sQ8_036tok/sQ8_0
Gemma 4 E4B14tok/sQ8_093tok/sQ8_0
LFM2.5 8B-A1B14tok/sQ8_089tok/sQ8_0
Llama 3.1 8B7tok/sQ6_K47tok/sQ6_K
Qwen2.5 0.5B79tok/sQ8_0519tok/sQ8_0
Qwen3.5 0.8B69tok/sQ8_0455tok/sQ8_0
Qwen3.5 2B55tok/sQ5_K_M363tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B30tok/sQ8_0197tok/sQ8_0
Mellum2.1 12B A2.5B Thinking22tok/sQ8_0146tok/sQ8_0
MiniCPM5 2B20tok/sQ8_0134tok/sQ8_0
LFM2.5 2.6B16tok/sQ8_0102tok/sQ8_0
LFM2.5 VL 3B16tok/sQ8_0102tok/sQ8_0
Kimi VL A3B14tok/smlx-8bit91tok/smlx-8bit
granite vision 4.1 4b12tok/sQ8_077tok/sQ8_0
granite 4.2 3b12tok/sQ8_076tok/sQ8_0
GLM 4.6V Flash11tok/sQ8_072tok/sQ8_0
DeepSeek R1 Distill Qwen 7B11tok/sQ8_071tok/sQ8_0
GLM 4.1V 9B Thinking10tok/smlx-8bit65tok/smlx-8bit
LFM2.5 24B A2B8tok/sQ8_053tok/sQ6_K
DeepSeek R1 Distill Llama 8B7tok/sQ8_043tok/sQ8_0
Ministral 3 8B Reasoning 25126tok/sQ8_041tok/sQ8_0
DeepSeek R1 Distill Qwen 14B4tok/sQ8_0offload
Devstral Small 25074tok/sQ8_0offload
Magistral Small 25064tok/sQ8_0offload
Magistral Small 25074tok/sQ8_0offload
Magistral Small 25094tok/sQ8_0offload
GLM 4.5V3tok/sQ4_K_Mwon't run
GLM 4.6V3tok/sQ4_K_Mwon't run
granite 4.2 30b3tok/sQ8_0offload
DeepSeek R1 Distill Llama 70B1tok/sQ8_0won't run
Mistral Medium 3.5 128B1tok/sQ4_K_Mwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.7won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run

Questions

Which is better for local AI, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 5090?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the NVIDIA GeForce RTX 5090 for speed. Choose the ASUS Ascent GX10 128GB to spend less.
Which can run bigger models, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 5090?
At 128k context the ASUS Ascent GX10 128GB runs 69 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 41; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 5090?
On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 6.6× as fast as the ASUS Ascent GX10 128GB (estimated, median across models).
What is the price difference between the ASUS Ascent GX10 128GB and the NVIDIA GeForce RTX 5090?
In Canada the ASUS Ascent GX10 128GB costs $8,299 at Amazon and the NVIDIA GeForce RTX 5090 $10,300 at Amazon: the ASUS Ascent GX10 128GB is $2,001 cheaper.

More comparisons